Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    giving advice or information

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on the preposition “with.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     split
    -0.06
     succeeded
    -0.06
    	dest
    -0.06
     solving
    -0.06
    ΡΙ
    -0.06
    MAP
    -0.06
     Moscow
    -0.06
     dividing
    -0.06
     Lamp
    -0.06
    Phi
    -0.06
    POSITIVE LOGITS
    /Form
    0.06
    ylabel
    0.06
    境
    0.06
    บบ
    0.06
     »↵↵
    0.06
    []={
    0.06
    .ListView
    0.06
    xsd
    0.06
    ]*(
    0.06
    .dataGridView
    0.06
    Act Density 0.019%

    No Known Activations